| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.716981132075472, | |
| "eval_steps": 500, | |
| "global_step": 1500, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.19908840954303741, | |
| "eval_runtime": 3.4704, | |
| "eval_samples_per_second": 893.271, | |
| "eval_steps_per_second": 18.73, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "grad_norm": 0.5476423501968384, | |
| "learning_rate": 1.371069182389937e-05, | |
| "loss": 0.3126, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.10444473475217819, | |
| "eval_runtime": 3.4097, | |
| "eval_samples_per_second": 909.18, | |
| "eval_steps_per_second": 19.063, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.07558976113796234, | |
| "eval_runtime": 3.3435, | |
| "eval_samples_per_second": 927.159, | |
| "eval_steps_per_second": 19.44, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "grad_norm": 0.5030196309089661, | |
| "learning_rate": 7.421383647798742e-06, | |
| "loss": 0.1205, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.06385820358991623, | |
| "eval_runtime": 3.3553, | |
| "eval_samples_per_second": 923.923, | |
| "eval_steps_per_second": 19.373, | |
| "step": 1272 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "grad_norm": 0.3436085283756256, | |
| "learning_rate": 1.1320754716981133e-06, | |
| "loss": 0.0871, | |
| "step": 1500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1590, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 391368939443328.0, | |
| "train_batch_size": 48, | |
| "trial_name": null, | |
| "trial_params": { | |
| "alpha": 0.20320499954717708, | |
| "num_train_epochs": 6, | |
| "temperature": 19 | |
| } | |
| } | |